# Does Prompt Formatting Have Any Impact on LLM Performance?

arXiv: https://arxiv.org/abs/2411.10541 · HTML: https://mlsanity.com/paper/2411.10541/

## Key facts

- Cited by 141 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 15 Nov 2024.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021)
- [Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting](https://mlsanity.com/paper/2310.11324/) (2023)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [Textbooks Are All You Need II: phi-1.5 technical report](https://mlsanity.com/paper/2309.05463/) (2023)
- [Stealing Part of a Production Language Model](https://mlsanity.com/paper/2403.06634/) (2024)
- [Mind Your Format: Towards Consistent Evaluation of In-Context Learning Improvements](https://mlsanity.com/paper/2401.06766/) (2024)
- [You don't need a personality test to know these models are unreliable: Assessing the Reliability of Large Language Models on Psychometric Instruments](https://mlsanity.com/paper/2311.09718/) (2023)
- [FIND: A Function Description Benchmark for Evaluating Interpretability Methods](https://mlsanity.com/paper/2309.03886/) (2023)

## Built on by (most cited first, 30 of 141)

- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models](https://mlsanity.com/paper/2501.13958/) (2025)
- [Self-Supervised Prompt Optimization](https://mlsanity.com/paper/2502.06855/) (2025)
- [CoAct-1: Computer-using Multi-Agent System with Coding Actions](https://mlsanity.com/paper/2508.03923/) (2025)
- [Policy-as-Prompt: Rethinking Content Moderation in the Age of Large Language Models](https://mlsanity.com/paper/2502.18695/) (2025)
- [Learning to Generate Structured Output with Schema Reinforcement Learning](https://mlsanity.com/paper/2502.18878/) (2025)
- [Trust Me, I'm Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer](https://mlsanity.com/paper/2502.12964/) (2025)
- [Towards LLMs Robustness to Changes in Prompt Format Styles](https://mlsanity.com/paper/2504.06969/) (2025)
- [Unable to Forget: Proactive Interference Reveals Working Memory Limits in LLMs Beyond Context Length](https://mlsanity.com/paper/2506.08184/) (2025)
- [The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs](https://mlsanity.com/paper/2502.04134/) (2025)
- [Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2507.17512/) (2025)
- [Adaptive Self-improvement LLM Agentic System for ML Library Development](https://mlsanity.com/paper/2502.02534/) (2025)
- [Beyond Prompt Content: Enhancing LLM Performance via Content-Format Integrated Prompt Optimization](https://mlsanity.com/paper/2502.04295/) (2025)
- [Token embeddings violate the manifold hypothesis](https://mlsanity.com/paper/2504.01002/) (2025)
- [Beyond Black-Box Benchmarking: Observability, Analytics, and Optimization of Agentic Systems](https://mlsanity.com/paper/2503.06745/) (2025)
- [Reassessing Extractive QA Datasets at Scale: LLM-as-a-Judge and In-Depth Analyses](https://mlsanity.com/paper/2504.11972/) (2025)
- [SCAM: A Real-World Typographic Robustness Evaluation for Multimodal Foundation Models](https://mlsanity.com/paper/2504.04893/) (2025)
- [Promptception: How Sensitive Are Large Multimodal Models to Prompts?](https://mlsanity.com/paper/2509.03986/) (2025)
- [Think Twice to See More: Iterative Visual Reasoning in Medical VLMs](https://mlsanity.com/paper/2510.10052/) (2025)
- [Tuning LLM Judge Design Decisions for 1/1000 of the Cost](https://mlsanity.com/paper/2501.17178/) (2025)
- [Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation](https://mlsanity.com/paper/2505.11604/) (2025)
- [Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding Data](https://mlsanity.com/paper/2503.05587/) (2025)
- [Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Models](https://mlsanity.com/paper/2503.07329/) (2025)
- [Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?](https://mlsanity.com/paper/2506.00751/) (2025)
- [Distributive Fairness in Large Language Models: Evaluating Alignment with Human Values](https://mlsanity.com/paper/2502.00313/) (2025)
- [Automated Profile Inference with Language Model Agents](https://mlsanity.com/paper/2505.12402/) (2025)
- [Decoupling Task-Solving and Output Formatting in LLM Generation](https://mlsanity.com/paper/2510.03595/) (2025)
- [Joint Localization and Activation Editing for Low-Resource Fine-Tuning](https://mlsanity.com/paper/2502.01179/) (2025)
- [InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition](https://mlsanity.com/paper/2505.15818/) (2025)
- [Existing Large Language Model Unlearning Evaluations Are Inconclusive](https://mlsanity.com/paper/2506.00688/) (2025)

## Abstract (arXiv)

In the realm of Large Language Models (LLMs), prompt optimization is crucial for model performance. Although previous research has explored aspects like rephrasing prompt contexts, using various prompting techniques (like in-context learning and chain-of-thought), and ordering few-shot examples, our understanding of LLM sensitivity to prompt templates remains limited. Therefore, this paper examines the impact of different prompt templates on LLM performance. We formatted the same contexts into various human-readable templates, including plain text, Markdown, JSON, and YAML, and evaluated their impact across tasks like natural language reasoning, code generation, and translation using OpenAI's GPT models. Experiments show that GPT-3.5-turbo's performance varies by up to 40% in a code translation task depending on the prompt template, while larger models like GPT-4 are more robust to these variations. Our analysis highlights the need to reconsider the use of fixed prompt templates, as different formats can significantly affect model performance.